how to use it ?
how to use the model and how did you convert it
It's a test model for https://github.com/leejet/stable-diffusion.cpp/pull/1053
Converted to BFL / Original Flux format using a modified version of https://github.com/kohya-ss/sd-scripts/blob/sd3/tools/convert_diffusers_to_flux.py
Quantized it with stable-diffusion.cpp.
Maybe it works with the GGUF node in ComfyUI, but I can't guarentee it, as I haven't tested.
It's a test model for https://github.com/leejet/stable-diffusion.cpp/pull/1053
Converted to BFL / Original Flux format using a modified version of https://github.com/kohya-ss/sd-scripts/blob/sd3/tools/convert_diffusers_to_flux.py
Quantized it with stable-diffusion.cpp.Maybe it works with the GGUF node in ComfyUI, but I can't guarentee it, as I haven't tested.
Hi, I found out a way of running this model on <4gb Vram. And I have not used any quantization.
Repo: https://github.com/Jit-Roy/WeeLLM
Use this repo. You will find out a kaggle link. You can directly use it there.